CN111179323A - Medical image feature point matching method, device, equipment and storage medium - Google Patents
Medical image feature point matching method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN111179323A CN111179323A CN201911390643.0A CN201911390643A CN111179323A CN 111179323 A CN111179323 A CN 111179323A CN 201911390643 A CN201911390643 A CN 201911390643A CN 111179323 A CN111179323 A CN 111179323A
- Authority
- CN
- China
- Prior art keywords
- feature point
- matching
- medical image
- polygon
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
Abstract
The invention discloses a medical image feature point matching method, a device, equipment and a storage medium. The method comprises the following steps: feature point extraction, feature polygon composition, matching polygon composition and similarity judgment. The method and the device perform feature point matching on each point in the first feature point set, enlarge the range of feature point matching, and adopt similarity judgment to further screen suspected feature points, thereby improving the accuracy of feature point matching and further improving the accuracy of image registration.
Description
Technical Field
The present invention relates to the field of image processing, and in particular, to a method, an apparatus, a device, and a storage medium for matching feature points of a medical image.
Background
In computer graphics, a conventional image feature point matching method generally uses only features of feature points to perform matching, and calculates a possible matching relationship by a method of searching neighboring points in a feature space of a feature structure of all feature points. Due to the geometric particularity of the medical images, the medical images of different staining schemes have natural shapes with multiple characteristic points with very close characteristics for the same specimen, so that misjudgment of the characteristic points is easy to generate.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art. Therefore, the invention provides a medical image feature point matching method which can effectively improve the accuracy of feature point matching.
The invention also provides a medical image feature point matching device.
The invention also provides a medical image feature point matching device.
The invention also provides a computer readable storage medium.
In a first aspect, an embodiment of the present invention provides a method for matching feature points of a medical image, including: the method comprises the following steps:
s1, extracting feature points, namely extracting the feature points from the two medical images to be registered respectively to obtain a first feature point set and a second feature point set;
s2, forming a target polygon by taking the feature points in the first feature point set and preset adjacent feature points as vertexes;
s3, forming matching polygons, searching preset proximity points of the vertexes of the target polygons in a second feature point set, and forming a plurality of matching polygons;
and S4, judging similarity, calculating Euclidean distances between the target polygon and each vertex of the matched polygon, judging whether a matched polygon similar to the target polygon exists in an error range, establishing a matching relation, and re-entering S2 until each feature point in the first feature point set is traversed.
The medical image feature point matching method provided by the embodiment of the invention at least has the following beneficial effects: and the matching feature points are further screened by judging whether the polygons formed by the matching feature points are similar, so that the accuracy of the matching of the feature points is improved.
Further, the target polygon is a triangle.
Further, in step S3, the number of the proximity points of the preset target polygon vertices is 2, and 8 matching polygons are formed.
Furthermore, the two medical images have the same shooting angle, the same shooting distance and different dyeing methods.
In a second aspect, an embodiment of the present invention provides a medical image feature point matching apparatus, including:
a feature point extraction module: the system comprises a first image acquisition unit, a second image acquisition unit, a registration unit and a registration unit, wherein the first image acquisition unit is used for acquiring a first medical image and a second medical image;
a target triangle selection module: the feature points in the first feature point set and preset adjacent feature points are used as vertexes to form a target polygon;
a matching triangle selection module: the second feature point set is used for searching preset proximity points of the vertexes of the target polygons and forming a plurality of matching polygons;
similarity comparison module: and the system is used for calculating Euclidean distances between the target polygon and each vertex of the matched polygon, judging whether a matched polygon similar to the target polygon exists in an error range, and establishing a matching relation.
The medical image feature point matching device of the embodiment of the invention at least has the following beneficial effects: and the matching feature points are further screened by the similarity comparison module, so that the accuracy of feature point matching is improved.
Drawings
Fig. 1 is a schematic flow chart illustrating an embodiment of a medical image feature point matching method according to the present invention;
fig. 2 is a block diagram of an embodiment of a medical image feature point matching apparatus according to the present invention.
Detailed Description
The concept and technical effects of the present invention will be clearly and completely described below in conjunction with the embodiments to fully understand the objects, features and effects of the present invention. It is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments, and those skilled in the art can obtain other embodiments without inventive effort based on the embodiments of the present invention, and all embodiments are within the protection scope of the present invention.
In the description of the present invention, if an orientation description is referred to, for example, the orientations or positional relationships indicated by "upper", "lower", "front", "rear", "left", "right", etc. are based on the orientations or positional relationships shown in the drawings, only for convenience of describing the present invention and simplifying the description, but not for indicating or implying that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention. If a feature is referred to as being "disposed," "secured," "connected," or "mounted" to another feature, it can be directly disposed, secured, or connected to the other feature or indirectly disposed, secured, connected, or mounted to the other feature.
In the description of the embodiments of the present invention, if "a number" is referred to, it means one or more, if "a plurality" is referred to, it means two or more, if "greater than", "less than" or "more than" is referred to, it is understood that the number is not included, and if "greater than", "lower" or "inner" is referred to, it is understood that the number is included. If reference is made to "first" or "second", this should be understood to distinguish between features and not to indicate or imply relative importance or to implicitly indicate the number of indicated features or to implicitly indicate the precedence of the indicated features.
The feature point matching method in the embodiment is particularly suitable for medical images, and images of the medical images have the characteristics of being shot by the same instrument, being the same in shooting angle and distance and being different in dyeing methods. Meanwhile, the medical image has many characteristic points with similar characteristics, and misjudgment is easy to occur when the characteristic points are matched.
Referring to fig. 1, a flowchart of a medical image feature point matching method according to an embodiment of the present invention is shown. The method specifically comprises the following steps:
s1, extracting feature points, namely extracting the feature points from the two medical images to be registered respectively to obtain a first feature point set and a second feature point set;
the feature point extraction is the prior art, and HOG features, LBP features, Haar features and the like can be adopted.
S2, forming a target polygon by taking the feature points in the first feature point set and preset adjacent feature points as vertexes;
for convenience of calculation, in this embodiment, the feature point PA in the first feature point set and the two feature points PB and PC closest to the PA point may be used as vertices to form a target triangle.
S3, forming matching polygons, searching preset proximity points of the vertexes of the target polygons in a second feature point set, and forming a plurality of matching polygons;
in the second feature point set, two feature points PA1 and PA2 closest to PA, two feature points PB1 and PB2 closest to PB, and two feature points PC1 and PC2 closest to PC are searched for, respectively.
Eight matching triangles are formed by taking one point of PA1 and PA2, one point of PB1 and PB2 and one point of PC1 and PC2 as vertexes.
And S4, judging similarity, calculating Euclidean distances between the target polygon and each vertex of the matched polygon, and judging whether a matched polygon similar to the target polygon exists in an error range.
And calculating Euclidean distances of all vertexes in the target triangle and the matched triangles, judging whether a triangle similar to that in the target triangle exists in the eight matched triangles or not, and if so, establishing a matching relation.
Re-enter S2 until each feature point in the first set of feature points is traversed.
The embodiment of the invention performs feature point matching on each point in the first feature point set, increases the range of feature point matching, and simultaneously adopts similarity judgment to further screen suspected feature points, thereby improving the accuracy of feature point matching and further improving the accuracy of image registration, and being particularly suitable for images in pathological sections, immunoblotting tests (Western Blot), flow charts and clone formation experiments.
Referring to fig. 2, fig. 2 shows a specific embodiment of a feature point matching apparatus for medical images, which includes: a feature point extraction module: the system comprises a first image acquisition unit, a second image acquisition unit, a registration unit and a registration unit, wherein the first image acquisition unit is used for acquiring a first medical image and a second medical image;
a target triangle selection module: the feature points in the first feature point set and preset adjacent feature points are used as vertexes to form a target polygon;
a matching triangle selection module: the second feature point set is used for searching preset proximity points of the vertexes of the target polygons and forming a plurality of matching polygons;
similarity comparison module: and the system is used for calculating Euclidean distances between the target polygon and each vertex of the matched polygon, judging whether a matched polygon similar to the target polygon exists in an error range, and establishing a matching relation.
The embodiment of the present invention further provides a medical image feature point matching device, including: at least one processor, and,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to enable the at least one processor to perform the medical image feature point matching method.
The embodiment of the invention also provides a computer-readable storage medium, wherein computer-executable instructions are stored in the computer-readable storage medium and used for enabling a computer to execute the medical image feature point matching method.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention. Furthermore, the embodiments of the present invention and the features of the embodiments may be combined with each other without conflict.
Claims (7)
1. A medical image feature point matching method is characterized by comprising the following steps:
s1, extracting feature points, namely extracting the feature points from the two medical images to be registered respectively to obtain a first feature point set and a second feature point set;
s2, forming a target polygon by taking the feature points in the first feature point set and preset adjacent feature points as vertexes;
s3, forming matching polygons, searching preset proximity points of the vertexes of the target polygons in a second feature point set, and forming a plurality of matching polygons;
and S4, judging similarity, calculating Euclidean distances between the target polygon and each vertex of the matched polygon, judging whether a matched polygon similar to the target polygon exists in an error range, establishing a matching relation, and re-entering S2 until each feature point in the first feature point set is traversed.
2. The method as claimed in claim 1, wherein the target polygon is a triangle.
3. The method as claimed in claim 1, wherein in step S3, the number of the neighboring points of the predetermined target polygon vertices is 2, and 8 matching polygons are formed.
4. The method according to claim 1, wherein the two medical images have the same shooting angle, the same shooting distance and different dyeing methods.
5. A medical image feature point matching apparatus, comprising:
a feature point extraction module: the system comprises a first image acquisition unit, a second image acquisition unit, a registration unit and a registration unit, wherein the first image acquisition unit is used for acquiring a first medical image and a second medical image;
a target triangle selection module: the feature points in the first feature point set and preset adjacent feature points are used as vertexes to form a target polygon;
a matching triangle selection module: the second feature point set is used for searching preset proximity points of the vertexes of the target polygons and forming a plurality of matching polygons;
similarity comparison module: and the system is used for calculating Euclidean distances between the target polygon and each vertex of the matched polygon, judging whether a matched polygon similar to the target polygon exists in an error range, and establishing a matching relation.
6. A medical image feature point matching apparatus, comprising:
at least one processor, and,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the medical image feature point matching method according to any one of claims 1 to 4.
7. A computer-readable storage medium storing computer-executable instructions for causing a computer to execute the medical image feature point matching method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911390643.0A CN111179323A (en) | 2019-12-30 | 2019-12-30 | Medical image feature point matching method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911390643.0A CN111179323A (en) | 2019-12-30 | 2019-12-30 | Medical image feature point matching method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111179323A true CN111179323A (en) | 2020-05-19 |
Family
ID=70652287
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911390643.0A Pending CN111179323A (en) | 2019-12-30 | 2019-12-30 | Medical image feature point matching method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111179323A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120114202A1 (en) * | 2010-11-10 | 2012-05-10 | Raytheon Company | Image registration system and method for registering images for deformable surfaces |
| CN103177444A (en) * | 2013-03-08 | 2013-06-26 | 中国电子科技集团公司第十四研究所 | Automatic SAR (synthetic-aperture radar) image rectification method |
| CN109389628A (en) * | 2018-09-07 | 2019-02-26 | 北京邮电大学 | Method for registering images, equipment and storage medium |
| CN110084254A (en) * | 2018-01-23 | 2019-08-02 | 北京国双科技有限公司 | Method and device is determined based on the similar image of social networks |
| CN110148133A (en) * | 2018-07-03 | 2019-08-20 | 北京邮电大学 | Circuit board relic image-recognizing method based on characteristic point and its structural relation |
-
2019
- 2019-12-30 CN CN201911390643.0A patent/CN111179323A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120114202A1 (en) * | 2010-11-10 | 2012-05-10 | Raytheon Company | Image registration system and method for registering images for deformable surfaces |
| CN103177444A (en) * | 2013-03-08 | 2013-06-26 | 中国电子科技集团公司第十四研究所 | Automatic SAR (synthetic-aperture radar) image rectification method |
| CN110084254A (en) * | 2018-01-23 | 2019-08-02 | 北京国双科技有限公司 | Method and device is determined based on the similar image of social networks |
| CN110148133A (en) * | 2018-07-03 | 2019-08-20 | 北京邮电大学 | Circuit board relic image-recognizing method based on characteristic point and its structural relation |
| CN109389628A (en) * | 2018-09-07 | 2019-02-26 | 北京邮电大学 | Method for registering images, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109741374B (en) | Point cloud registration rotation transformation method, point cloud registration equipment and readable storage medium | |
| EP2538242B1 (en) | Depth measurement quality enhancement. | |
| CN106991407B (en) | A kind of method and device of lane detection | |
| CN112381847B (en) | Pipeline end space pose measurement method and system | |
| EP2166375A2 (en) | System and method of extracting plane features | |
| EP2887315A1 (en) | Calibration device, method for implementing calibration, program and camera for movable body | |
| US20230260216A1 (en) | Point cloud annotation device, method, and program | |
| WO2014123619A1 (en) | System and method for identifying similarities in different images | |
| WO2015035462A1 (en) | Point feature based 2d-3d registration | |
| CN104949657A (en) | Object detection device, object detection method, and computer readable storage medium comprising objection detection program | |
| CN111105452A (en) | High-low resolution fusion stereo matching method based on binocular vision | |
| CN109785370A (en) | A kind of weak texture image method for registering based on space time series model | |
| KR101925289B1 (en) | Method and apparatus for identifying location/angle of terminal | |
| Cui et al. | Global propagation of affine invariant features for robust matching | |
| CN111179323A (en) | Medical image feature point matching method, device, equipment and storage medium | |
| CN107765257A (en) | A kind of laser acquisition and measuring method based on the calibration of reflected intensity accessory external | |
| CN115239821B (en) | Parameter information determination method and device, vehicle, electronic equipment and storage medium | |
| US8897547B2 (en) | Precision improving device for three dimensional topographical data, precision improving method for three dimensional topographical data and recording medium | |
| CN111178366B (en) | Mobile robot positioning method and mobile robot | |
| CN111429399B (en) | Linear detection method and device | |
| JP5991166B2 (en) | 3D position measurement device, 3D position measurement method, and 3D position measurement program | |
| CN113298869B (en) | Distance measuring method, distance measuring device, computer device, and storage medium | |
| CN117253179B (en) | Distribution line bird nest detection method, storage medium and electronic equipment | |
| CN112270372B (en) | Method, device, computer equipment and medium for determining target object | |
| CN117789198B (en) | Method for realizing point cloud degradation detection based on 4D millimeter wave imaging radar |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 201799 room 450, area F, 4 / F, building 3, 5399 Jiasong Middle Road, Zhaoxiang Town, Qingpu District, Shanghai Applicant after: Shanghai Huayan Digital Medical Technology Co.,Ltd. Applicant after: Yu Guanzhen Applicant after: Chen Ying Applicant after: Gao Yunshu Address before: Room jt3028, 1st floor, building 1, No. 1185, Huyi Road, Jiading District, Shanghai 200233 Applicant before: Shanghai Yanjing Medical Technology Co.,Ltd. Applicant before: Yu Guanzhen Applicant before: Chen Ying Applicant before: Gao Yunshu |
|
| CB02 | Change of applicant information | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220930 Address after: Room 1201, Building 19, No. 238, Jiangchang Third Road, Jing'an District, Shanghai, 200040 Applicant after: Shanghai Jingguan Biotechnology Co.,Ltd. Address before: 201799 room 450, area F, 4 / F, building 3, 5399 Jiasong Middle Road, Zhaoxiang Town, Qingpu District, Shanghai Applicant before: Shanghai Huayan Digital Medical Technology Co.,Ltd. Applicant before: Yu Guanzhen Applicant before: Chen Ying Applicant before: Gao Yunshu |
|
| TA01 | Transfer of patent application right |